[llvm] [DAG] SimplifyMultipleUseDemandedBits - ignore SRL node if we're just demanding known sign bits (PR #114389)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Oct 31 03:55:33 PDT 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-x86
Author: Simon Pilgrim (RKSimon)
<details>
<summary>Changes</summary>
Check to see if we are only demanding (shifted) signbits from a SRL node that are also signbits in the source node.
We can't demand any upper zero bits that the SRL will shift in (up to max shift amount), and the lower demanded bits bound must already be all signbits.
---
Patch is 58.01 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/114389.diff
6 Files Affected:
- (modified) llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp (+18)
- (modified) llvm/test/CodeGen/AMDGPU/div-rem-by-constant-64.ll (+22-28)
- (modified) llvm/test/CodeGen/AMDGPU/fptoi.i128.ll (+72-80)
- (modified) llvm/test/CodeGen/RISCV/pr95284.ll (+10-12)
- (modified) llvm/test/CodeGen/RISCV/urem-seteq-illegal-types.ll (+11-11)
- (modified) llvm/test/CodeGen/X86/scmp.ll (+313-324)
``````````diff
diff --git a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
index fabcbc5f0e856d..de291493faddbb 100644
--- a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
@@ -808,6 +808,24 @@ SDValue TargetLowering::SimplifyMultipleUseDemandedBits(
}
break;
}
+ case ISD::SRL: {
+ // If we are only demanding sign bits then we can use the shift source
+ // directly.
+ if (std::optional<uint64_t> MaxSA =
+ DAG.getValidMaximumShiftAmount(Op, DemandedElts, Depth + 1)) {
+ SDValue Op0 = Op.getOperand(0);
+ unsigned ShAmt = *MaxSA;
+ unsigned NumSignBits =
+ DAG.ComputeNumSignBits(Op0, DemandedElts, Depth + 1);
+ unsigned LoDemandedBits = DemandedBits.countr_zero();
+ unsigned HiDemandedBits = DemandedBits.countl_zero();
+ // Must already be signbits in DemandedBits bounds, and can't demand any
+ // shifted in zeroes.
+ if (HiDemandedBits >= ShAmt && LoDemandedBits >= (BitWidth - NumSignBits))
+ return Op0;
+ }
+ break;
+ }
case ISD::SETCC: {
SDValue Op0 = Op.getOperand(0);
SDValue Op1 = Op.getOperand(1);
diff --git a/llvm/test/CodeGen/AMDGPU/div-rem-by-constant-64.ll b/llvm/test/CodeGen/AMDGPU/div-rem-by-constant-64.ll
index 4143c65a840d71..662de47413654f 100644
--- a/llvm/test/CodeGen/AMDGPU/div-rem-by-constant-64.ll
+++ b/llvm/test/CodeGen/AMDGPU/div-rem-by-constant-64.ll
@@ -1052,16 +1052,15 @@ define noundef i64 @srem64_i32max(i64 noundef %i) {
; GFX9-NEXT: s_mov_b32 s6, 0x80000001
; GFX9-NEXT: v_ashrrev_i32_e32 v6, 31, v1
; GFX9-NEXT: v_mad_u64_u32 v[4:5], s[4:5], v1, 3, v[2:3]
-; GFX9-NEXT: v_mul_i32_i24_e32 v8, 3, v6
-; GFX9-NEXT: v_lshl_add_u32 v9, v6, 31, v6
-; GFX9-NEXT: v_mov_b32_e32 v10, v5
+; GFX9-NEXT: v_lshl_add_u32 v8, v6, 31, v6
+; GFX9-NEXT: v_mad_u64_u32 v[6:7], s[4:5], v6, 3, 0
+; GFX9-NEXT: v_mov_b32_e32 v9, v5
; GFX9-NEXT: v_mov_b32_e32 v5, v3
; GFX9-NEXT: v_mad_u64_u32 v[2:3], s[4:5], v0, s6, v[4:5]
-; GFX9-NEXT: v_mad_u64_u32 v[6:7], s[4:5], v6, 3, 0
-; GFX9-NEXT: v_mov_b32_e32 v2, v3
-; GFX9-NEXT: v_add_co_u32_e32 v2, vcc, v10, v2
-; GFX9-NEXT: v_add3_u32 v7, v7, v9, v8
+; GFX9-NEXT: v_add3_u32 v7, v7, v8, v6
; GFX9-NEXT: v_mad_u64_u32 v[4:5], s[4:5], v0, -1, v[6:7]
+; GFX9-NEXT: v_mov_b32_e32 v2, v3
+; GFX9-NEXT: v_add_co_u32_e32 v2, vcc, v9, v2
; GFX9-NEXT: v_addc_co_u32_e64 v3, s[4:5], 0, 0, vcc
; GFX9-NEXT: v_mad_u64_u32 v[2:3], s[4:5], v1, s6, v[2:3]
; GFX9-NEXT: v_sub_u32_e32 v5, v5, v1
@@ -1085,10 +1084,9 @@ define noundef i64 @srem64_i32max(i64 noundef %i) {
; GFX942: ; %bb.0: ; %entry
; GFX942-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX942-NEXT: v_ashrrev_i32_e32 v2, 31, v1
-; GFX942-NEXT: v_mul_i32_i24_e32 v4, 3, v2
-; GFX942-NEXT: v_lshl_add_u32 v5, v2, 31, v2
+; GFX942-NEXT: v_lshl_add_u32 v4, v2, 31, v2
; GFX942-NEXT: v_mad_u64_u32 v[2:3], s[0:1], v2, 3, 0
-; GFX942-NEXT: v_add3_u32 v3, v3, v5, v4
+; GFX942-NEXT: v_add3_u32 v3, v3, v4, v2
; GFX942-NEXT: v_mul_hi_u32 v4, v0, 3
; GFX942-NEXT: v_mov_b32_e32 v5, 0
; GFX942-NEXT: v_mad_u64_u32 v[6:7], s[0:1], v1, 3, v[4:5]
@@ -1125,17 +1123,16 @@ define noundef i64 @srem64_i32max(i64 noundef %i) {
; GFX1030-NEXT: v_mul_hi_u32 v2, v0, 3
; GFX1030-NEXT: v_mov_b32_e32 v3, 0
; GFX1030-NEXT: v_ashrrev_i32_e32 v6, 31, v1
-; GFX1030-NEXT: v_mul_i32_i24_e32 v7, 3, v6
; GFX1030-NEXT: v_mad_u64_u32 v[4:5], null, v1, 3, v[2:3]
-; GFX1030-NEXT: v_mov_b32_e32 v8, v5
+; GFX1030-NEXT: v_mov_b32_e32 v7, v5
; GFX1030-NEXT: v_mov_b32_e32 v5, v3
; GFX1030-NEXT: v_mad_u64_u32 v[2:3], null, v6, 3, 0
; GFX1030-NEXT: v_lshl_add_u32 v6, v6, 31, v6
; GFX1030-NEXT: v_mad_u64_u32 v[4:5], null, 0x80000001, v0, v[4:5]
-; GFX1030-NEXT: v_add3_u32 v3, v3, v6, v7
+; GFX1030-NEXT: v_add3_u32 v3, v3, v6, v2
; GFX1030-NEXT: v_mov_b32_e32 v4, v5
; GFX1030-NEXT: v_mad_u64_u32 v[2:3], null, v0, -1, v[2:3]
-; GFX1030-NEXT: v_add_co_u32 v4, s4, v8, v4
+; GFX1030-NEXT: v_add_co_u32 v4, s4, v7, v4
; GFX1030-NEXT: v_add_co_ci_u32_e64 v5, null, 0, 0, s4
; GFX1030-NEXT: v_sub_nc_u32_e32 v6, v3, v1
; GFX1030-NEXT: v_mad_u64_u32 v[3:4], null, 0x80000001, v1, v[4:5]
@@ -1167,16 +1164,15 @@ define noundef i64 @sdiv64_i32max(i64 noundef %i) {
; GFX9-NEXT: s_mov_b32 s6, 0x80000001
; GFX9-NEXT: v_ashrrev_i32_e32 v6, 31, v1
; GFX9-NEXT: v_mad_u64_u32 v[4:5], s[4:5], v1, 3, v[2:3]
-; GFX9-NEXT: v_mul_i32_i24_e32 v8, 3, v6
-; GFX9-NEXT: v_lshl_add_u32 v9, v6, 31, v6
-; GFX9-NEXT: v_mov_b32_e32 v10, v5
+; GFX9-NEXT: v_lshl_add_u32 v8, v6, 31, v6
+; GFX9-NEXT: v_mad_u64_u32 v[6:7], s[4:5], v6, 3, 0
+; GFX9-NEXT: v_mov_b32_e32 v9, v5
; GFX9-NEXT: v_mov_b32_e32 v5, v3
; GFX9-NEXT: v_mad_u64_u32 v[2:3], s[4:5], v0, s6, v[4:5]
-; GFX9-NEXT: v_mad_u64_u32 v[6:7], s[4:5], v6, 3, 0
-; GFX9-NEXT: v_mov_b32_e32 v2, v3
-; GFX9-NEXT: v_add_co_u32_e32 v2, vcc, v10, v2
-; GFX9-NEXT: v_add3_u32 v7, v7, v9, v8
+; GFX9-NEXT: v_add3_u32 v7, v7, v8, v6
; GFX9-NEXT: v_mad_u64_u32 v[4:5], s[4:5], v0, -1, v[6:7]
+; GFX9-NEXT: v_mov_b32_e32 v2, v3
+; GFX9-NEXT: v_add_co_u32_e32 v2, vcc, v9, v2
; GFX9-NEXT: v_addc_co_u32_e64 v3, s[4:5], 0, 0, vcc
; GFX9-NEXT: v_mad_u64_u32 v[2:3], s[4:5], v1, s6, v[2:3]
; GFX9-NEXT: v_sub_u32_e32 v5, v5, v1
@@ -1195,10 +1191,9 @@ define noundef i64 @sdiv64_i32max(i64 noundef %i) {
; GFX942: ; %bb.0: ; %entry
; GFX942-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX942-NEXT: v_ashrrev_i32_e32 v2, 31, v1
-; GFX942-NEXT: v_mul_i32_i24_e32 v4, 3, v2
-; GFX942-NEXT: v_lshl_add_u32 v5, v2, 31, v2
+; GFX942-NEXT: v_lshl_add_u32 v4, v2, 31, v2
; GFX942-NEXT: v_mad_u64_u32 v[2:3], s[0:1], v2, 3, 0
-; GFX942-NEXT: v_add3_u32 v3, v3, v5, v4
+; GFX942-NEXT: v_add3_u32 v3, v3, v4, v2
; GFX942-NEXT: v_mul_hi_u32 v4, v0, 3
; GFX942-NEXT: v_mov_b32_e32 v5, 0
; GFX942-NEXT: v_mad_u64_u32 v[6:7], s[0:1], v1, 3, v[4:5]
@@ -1227,17 +1222,16 @@ define noundef i64 @sdiv64_i32max(i64 noundef %i) {
; GFX1030-NEXT: v_mul_hi_u32 v2, v0, 3
; GFX1030-NEXT: v_mov_b32_e32 v3, 0
; GFX1030-NEXT: v_ashrrev_i32_e32 v6, 31, v1
-; GFX1030-NEXT: v_mul_i32_i24_e32 v7, 3, v6
; GFX1030-NEXT: v_mad_u64_u32 v[4:5], null, v1, 3, v[2:3]
-; GFX1030-NEXT: v_mov_b32_e32 v8, v5
+; GFX1030-NEXT: v_mov_b32_e32 v7, v5
; GFX1030-NEXT: v_mov_b32_e32 v5, v3
; GFX1030-NEXT: v_mad_u64_u32 v[2:3], null, v6, 3, 0
; GFX1030-NEXT: v_lshl_add_u32 v6, v6, 31, v6
; GFX1030-NEXT: v_mad_u64_u32 v[4:5], null, 0x80000001, v0, v[4:5]
-; GFX1030-NEXT: v_add3_u32 v3, v3, v6, v7
+; GFX1030-NEXT: v_add3_u32 v3, v3, v6, v2
; GFX1030-NEXT: v_mov_b32_e32 v4, v5
; GFX1030-NEXT: v_mad_u64_u32 v[2:3], null, v0, -1, v[2:3]
-; GFX1030-NEXT: v_add_co_u32 v4, s4, v8, v4
+; GFX1030-NEXT: v_add_co_u32 v4, s4, v7, v4
; GFX1030-NEXT: v_add_co_ci_u32_e64 v5, null, 0, 0, s4
; GFX1030-NEXT: v_sub_nc_u32_e32 v6, v3, v1
; GFX1030-NEXT: v_mad_u64_u32 v[3:4], null, 0x80000001, v1, v[4:5]
diff --git a/llvm/test/CodeGen/AMDGPU/fptoi.i128.ll b/llvm/test/CodeGen/AMDGPU/fptoi.i128.ll
index 786fe03164690e..68ebc21e2ba4d6 100644
--- a/llvm/test/CodeGen/AMDGPU/fptoi.i128.ll
+++ b/llvm/test/CodeGen/AMDGPU/fptoi.i128.ll
@@ -37,12 +37,11 @@ define i128 @fptosi_f64_to_i128(double %x) {
; SDAG-NEXT: ; %bb.2: ; %fp-to-i-if-end9
; SDAG-NEXT: v_cndmask_b32_e64 v0, 0, 1, vcc
; SDAG-NEXT: v_add_co_u32_e64 v9, s[4:5], -1, v0
-; SDAG-NEXT: v_addc_co_u32_e64 v10, s[4:5], 0, -1, s[4:5]
; SDAG-NEXT: s_mov_b64 s[4:5], 0x432
; SDAG-NEXT: v_and_b32_e32 v0, 0xfffff, v5
; SDAG-NEXT: v_cmp_lt_u64_e64 s[4:5], s[4:5], v[6:7]
; SDAG-NEXT: v_cndmask_b32_e64 v8, -1, 0, vcc
-; SDAG-NEXT: v_cndmask_b32_e64 v11, -1, 1, vcc
+; SDAG-NEXT: v_cndmask_b32_e64 v10, -1, 1, vcc
; SDAG-NEXT: v_or_b32_e32 v5, 0x100000, v0
; SDAG-NEXT: ; implicit-def: $vgpr0_vgpr1
; SDAG-NEXT: ; implicit-def: $vgpr2_vgpr3
@@ -62,34 +61,33 @@ define i128 @fptosi_f64_to_i128(double %x) {
; SDAG-NEXT: v_cndmask_b32_e64 v2, v2, v0, s[4:5]
; SDAG-NEXT: v_lshlrev_b64 v[0:1], v7, v[4:5]
; SDAG-NEXT: v_cndmask_b32_e64 v2, 0, v2, s[6:7]
-; SDAG-NEXT: v_cndmask_b32_e64 v12, 0, v0, s[4:5]
+; SDAG-NEXT: v_cndmask_b32_e64 v11, 0, v0, s[4:5]
; SDAG-NEXT: v_cndmask_b32_e64 v7, 0, v1, s[4:5]
-; SDAG-NEXT: v_mad_u64_u32 v[0:1], s[4:5], v12, v11, 0
+; SDAG-NEXT: v_mad_u64_u32 v[0:1], s[4:5], v11, v10, 0
; SDAG-NEXT: v_mov_b32_e32 v3, 0
-; SDAG-NEXT: v_mul_lo_u32 v13, v8, v2
-; SDAG-NEXT: v_mad_u64_u32 v[4:5], s[4:5], v11, v2, 0
+; SDAG-NEXT: v_mul_lo_u32 v12, v8, v2
+; SDAG-NEXT: v_mad_u64_u32 v[4:5], s[4:5], v10, v2, 0
; SDAG-NEXT: v_mov_b32_e32 v2, v1
-; SDAG-NEXT: v_mul_lo_u32 v6, v11, v6
-; SDAG-NEXT: v_mad_u64_u32 v[1:2], s[4:5], v7, v11, v[2:3]
-; SDAG-NEXT: v_mul_lo_u32 v10, v10, v12
-; SDAG-NEXT: v_add3_u32 v5, v5, v6, v13
+; SDAG-NEXT: v_mul_lo_u32 v6, v10, v6
+; SDAG-NEXT: v_mad_u64_u32 v[1:2], s[4:5], v7, v10, v[2:3]
+; SDAG-NEXT: v_mul_lo_u32 v10, v9, v7
+; SDAG-NEXT: v_add3_u32 v5, v5, v6, v12
; SDAG-NEXT: v_mov_b32_e32 v6, v2
; SDAG-NEXT: v_mov_b32_e32 v2, v3
-; SDAG-NEXT: v_mad_u64_u32 v[1:2], s[4:5], v12, v8, v[1:2]
-; SDAG-NEXT: v_mad_u64_u32 v[3:4], s[4:5], v9, v12, v[4:5]
+; SDAG-NEXT: v_mad_u64_u32 v[1:2], s[4:5], v11, v8, v[1:2]
+; SDAG-NEXT: v_mad_u64_u32 v[3:4], s[4:5], v9, v11, v[4:5]
; SDAG-NEXT: v_add_co_u32_e64 v5, s[4:5], v6, v2
; SDAG-NEXT: v_addc_co_u32_e64 v6, s[4:5], 0, 0, s[4:5]
-; SDAG-NEXT: v_mul_lo_u32 v9, v9, v7
+; SDAG-NEXT: v_mul_lo_u32 v9, v9, v11
; SDAG-NEXT: v_mad_u64_u32 v[5:6], s[4:5], v7, v8, v[5:6]
-; SDAG-NEXT: ; implicit-def: $vgpr11
; SDAG-NEXT: ; implicit-def: $vgpr8
-; SDAG-NEXT: v_add3_u32 v4, v10, v4, v9
+; SDAG-NEXT: v_add3_u32 v4, v9, v4, v10
; SDAG-NEXT: v_add_co_u32_e64 v2, s[4:5], v5, v3
; SDAG-NEXT: v_addc_co_u32_e64 v3, s[4:5], v6, v4, s[4:5]
; SDAG-NEXT: ; implicit-def: $vgpr6_vgpr7
; SDAG-NEXT: ; implicit-def: $vgpr4_vgpr5
-; SDAG-NEXT: ; implicit-def: $vgpr9
; SDAG-NEXT: ; implicit-def: $vgpr10
+; SDAG-NEXT: ; implicit-def: $vgpr9
; SDAG-NEXT: .LBB0_4: ; %Flow
; SDAG-NEXT: s_andn2_saveexec_b64 s[12:13], s[12:13]
; SDAG-NEXT: s_cbranch_execz .LBB0_6
@@ -102,9 +100,9 @@ define i128 @fptosi_f64_to_i128(double %x) {
; SDAG-NEXT: v_cndmask_b32_e64 v1, 0, v1, s[4:5]
; SDAG-NEXT: v_cndmask_b32_e64 v6, v0, v4, s[6:7]
; SDAG-NEXT: v_cndmask_b32_e64 v5, v1, v5, s[6:7]
-; SDAG-NEXT: v_mad_u64_u32 v[0:1], s[4:5], v6, v11, 0
+; SDAG-NEXT: v_mad_u64_u32 v[0:1], s[4:5], v6, v10, 0
; SDAG-NEXT: v_mov_b32_e32 v2, 0
-; SDAG-NEXT: v_mad_u64_u32 v[3:4], s[4:5], v5, v11, v[1:2]
+; SDAG-NEXT: v_mad_u64_u32 v[3:4], s[4:5], v5, v10, v[1:2]
; SDAG-NEXT: v_mov_b32_e32 v7, v4
; SDAG-NEXT: v_mov_b32_e32 v4, v2
; SDAG-NEXT: v_mad_u64_u32 v[1:2], s[4:5], v6, v8, v[3:4]
@@ -112,7 +110,7 @@ define i128 @fptosi_f64_to_i128(double %x) {
; SDAG-NEXT: v_addc_co_u32_e64 v3, s[4:5], 0, 0, s[4:5]
; SDAG-NEXT: v_mad_u64_u32 v[2:3], s[4:5], v5, v8, v[2:3]
; SDAG-NEXT: v_mad_u64_u32 v[2:3], s[4:5], v9, v6, v[2:3]
-; SDAG-NEXT: v_mad_u64_u32 v[3:4], s[4:5], v10, v6, v[3:4]
+; SDAG-NEXT: v_mad_u64_u32 v[3:4], s[4:5], v9, v6, v[3:4]
; SDAG-NEXT: v_mad_i32_i24 v3, v9, v5, v3
; SDAG-NEXT: .LBB0_6: ; %Flow1
; SDAG-NEXT: s_or_b64 exec, exec, s[12:13]
@@ -409,12 +407,11 @@ define i128 @fptoui_f64_to_i128(double %x) {
; SDAG-NEXT: ; %bb.2: ; %fp-to-i-if-end9
; SDAG-NEXT: v_cndmask_b32_e64 v0, 0, 1, vcc
; SDAG-NEXT: v_add_co_u32_e64 v9, s[4:5], -1, v0
-; SDAG-NEXT: v_addc_co_u32_e64 v10, s[4:5], 0, -1, s[4:5]
; SDAG-NEXT: s_mov_b64 s[4:5], 0x432
; SDAG-NEXT: v_and_b32_e32 v0, 0xfffff, v5
; SDAG-NEXT: v_cmp_lt_u64_e64 s[4:5], s[4:5], v[6:7]
; SDAG-NEXT: v_cndmask_b32_e64 v8, -1, 0, vcc
-; SDAG-NEXT: v_cndmask_b32_e64 v11, -1, 1, vcc
+; SDAG-NEXT: v_cndmask_b32_e64 v10, -1, 1, vcc
; SDAG-NEXT: v_or_b32_e32 v5, 0x100000, v0
; SDAG-NEXT: ; implicit-def: $vgpr0_vgpr1
; SDAG-NEXT: ; implicit-def: $vgpr2_vgpr3
@@ -434,34 +431,33 @@ define i128 @fptoui_f64_to_i128(double %x) {
; SDAG-NEXT: v_cndmask_b32_e64 v2, v2, v0, s[4:5]
; SDAG-NEXT: v_lshlrev_b64 v[0:1], v7, v[4:5]
; SDAG-NEXT: v_cndmask_b32_e64 v2, 0, v2, s[6:7]
-; SDAG-NEXT: v_cndmask_b32_e64 v12, 0, v0, s[4:5]
+; SDAG-NEXT: v_cndmask_b32_e64 v11, 0, v0, s[4:5]
; SDAG-NEXT: v_cndmask_b32_e64 v7, 0, v1, s[4:5]
-; SDAG-NEXT: v_mad_u64_u32 v[0:1], s[4:5], v12, v11, 0
+; SDAG-NEXT: v_mad_u64_u32 v[0:1], s[4:5], v11, v10, 0
; SDAG-NEXT: v_mov_b32_e32 v3, 0
-; SDAG-NEXT: v_mul_lo_u32 v13, v8, v2
-; SDAG-NEXT: v_mad_u64_u32 v[4:5], s[4:5], v11, v2, 0
+; SDAG-NEXT: v_mul_lo_u32 v12, v8, v2
+; SDAG-NEXT: v_mad_u64_u32 v[4:5], s[4:5], v10, v2, 0
; SDAG-NEXT: v_mov_b32_e32 v2, v1
-; SDAG-NEXT: v_mul_lo_u32 v6, v11, v6
-; SDAG-NEXT: v_mad_u64_u32 v[1:2], s[4:5], v7, v11, v[2:3]
-; SDAG-NEXT: v_mul_lo_u32 v10, v10, v12
-; SDAG-NEXT: v_add3_u32 v5, v5, v6, v13
+; SDAG-NEXT: v_mul_lo_u32 v6, v10, v6
+; SDAG-NEXT: v_mad_u64_u32 v[1:2], s[4:5], v7, v10, v[2:3]
+; SDAG-NEXT: v_mul_lo_u32 v10, v9, v7
+; SDAG-NEXT: v_add3_u32 v5, v5, v6, v12
; SDAG-NEXT: v_mov_b32_e32 v6, v2
; SDAG-NEXT: v_mov_b32_e32 v2, v3
-; SDAG-NEXT: v_mad_u64_u32 v[1:2], s[4:5], v12, v8, v[1:2]
-; SDAG-NEXT: v_mad_u64_u32 v[3:4], s[4:5], v9, v12, v[4:5]
+; SDAG-NEXT: v_mad_u64_u32 v[1:2], s[4:5], v11, v8, v[1:2]
+; SDAG-NEXT: v_mad_u64_u32 v[3:4], s[4:5], v9, v11, v[4:5]
; SDAG-NEXT: v_add_co_u32_e64 v5, s[4:5], v6, v2
; SDAG-NEXT: v_addc_co_u32_e64 v6, s[4:5], 0, 0, s[4:5]
-; SDAG-NEXT: v_mul_lo_u32 v9, v9, v7
+; SDAG-NEXT: v_mul_lo_u32 v9, v9, v11
; SDAG-NEXT: v_mad_u64_u32 v[5:6], s[4:5], v7, v8, v[5:6]
-; SDAG-NEXT: ; implicit-def: $vgpr11
; SDAG-NEXT: ; implicit-def: $vgpr8
-; SDAG-NEXT: v_add3_u32 v4, v10, v4, v9
+; SDAG-NEXT: v_add3_u32 v4, v9, v4, v10
; SDAG-NEXT: v_add_co_u32_e64 v2, s[4:5], v5, v3
; SDAG-NEXT: v_addc_co_u32_e64 v3, s[4:5], v6, v4, s[4:5]
; SDAG-NEXT: ; implicit-def: $vgpr6_vgpr7
; SDAG-NEXT: ; implicit-def: $vgpr4_vgpr5
-; SDAG-NEXT: ; implicit-def: $vgpr9
; SDAG-NEXT: ; implicit-def: $vgpr10
+; SDAG-NEXT: ; implicit-def: $vgpr9
; SDAG-NEXT: .LBB1_4: ; %Flow
; SDAG-NEXT: s_andn2_saveexec_b64 s[12:13], s[12:13]
; SDAG-NEXT: s_cbranch_execz .LBB1_6
@@ -474,9 +470,9 @@ define i128 @fptoui_f64_to_i128(double %x) {
; SDAG-NEXT: v_cndmask_b32_e64 v1, 0, v1, s[4:5]
; SDAG-NEXT: v_cndmask_b32_e64 v6, v0, v4, s[6:7]
; SDAG-NEXT: v_cndmask_b32_e64 v5, v1, v5, s[6:7]
-; SDAG-NEXT: v_mad_u64_u32 v[0:1], s[4:5], v6, v11, 0
+; SDAG-NEXT: v_mad_u64_u32 v[0:1], s[4:5], v6, v10, 0
; SDAG-NEXT: v_mov_b32_e32 v2, 0
-; SDAG-NEXT: v_mad_u64_u32 v[3:4], s[4:5], v5, v11, v[1:2]
+; SDAG-NEXT: v_mad_u64_u32 v[3:4], s[4:5], v5, v10, v[1:2]
; SDAG-NEXT: v_mov_b32_e32 v7, v4
; SDAG-NEXT: v_mov_b32_e32 v4, v2
; SDAG-NEXT: v_mad_u64_u32 v[1:2], s[4:5], v6, v8, v[3:4]
@@ -484,7 +480,7 @@ define i128 @fptoui_f64_to_i128(double %x) {
; SDAG-NEXT: v_addc_co_u32_e64 v3, s[4:5], 0, 0, s[4:5]
; SDAG-NEXT: v_mad_u64_u32 v[2:3], s[4:5], v5, v8, v[2:3]
; SDAG-NEXT: v_mad_u64_u32 v[2:3], s[4:5], v9, v6, v[2:3]
-; SDAG-NEXT: v_mad_u64_u32 v[3:4], s[4:5], v10, v6, v[3:4]
+; SDAG-NEXT: v_mad_u64_u32 v[3:4], s[4:5], v9, v6, v[3:4]
; SDAG-NEXT: v_mad_i32_i24 v3, v9, v5, v3
; SDAG-NEXT: .LBB1_6: ; %Flow1
; SDAG-NEXT: s_or_b64 exec, exec, s[12:13]
@@ -780,7 +776,6 @@ define i128 @fptosi_f32_to_i128(float %x) {
; SDAG-NEXT: ; %bb.2: ; %fp-to-i-if-end9
; SDAG-NEXT: v_cndmask_b32_e64 v0, 0, 1, vcc
; SDAG-NEXT: v_add_co_u32_e64 v9, s[4:5], -1, v0
-; SDAG-NEXT: v_addc_co_u32_e64 v11, s[4:5], 0, -1, s[4:5]
; SDAG-NEXT: s_mov_b64 s[4:5], 0x95
; SDAG-NEXT: v_and_b32_e32 v0, 0x7fffff, v4
; SDAG-NEXT: v_cmp_lt_u64_e64 s[4:5], s[4:5], v[5:6]
@@ -806,24 +801,24 @@ define i128 @fptosi_f32_to_i128(float %x) {
; SDAG-NEXT: v_cndmask_b32_e64 v2, v2, v0, s[4:5]
; SDAG-NEXT: v_lshlrev_b64 v[0:1], v4, v[6:7]
; SDAG-NEXT: v_cndmask_b32_e64 v2, 0, v2, s[6:7]
-; SDAG-NEXT: v_cndmask_b32_e64 v13, 0, v0, s[4:5]
-; SDAG-NEXT: v_cndmask_b32_e64 v12, 0, v1, s[4:5]
-; SDAG-NEXT: v_mad_u64_u32 v[0:1], s[4:5], v13, v10, 0
-; SDAG-NEXT: v_mul_lo_u32 v14, v8, v2
-; SDAG-NEXT: v_mul_lo_u32 v15, v10, v3
+; SDAG-NEXT: v_cndmask_b32_e64 v12, 0, v0, s[4:5]
+; SDAG-NEXT: v_cndmask_b32_e64 v11, 0, v1, s[4:5]
+; SDAG-NEXT: v_mad_u64_u32 v[0:1], s[4:5], v12, v10, 0
+; SDAG-NEXT: v_mul_lo_u32 v13, v8, v2
+; SDAG-NEXT: v_mul_lo_u32 v14, v10, v3
; SDAG-NEXT: v_mov_b32_e32 v6, v1
-; SDAG-NEXT: v_mad_u64_u32 v[4:5], s[4:5], v12, v10, v[6:7]
+; SDAG-NEXT: v_mad_u64_u32 v[4:5], s[4:5], v11, v10, v[6:7]
; SDAG-NEXT: v_mad_u64_u32 v[2:3], s[4:5], v10, v2, 0
; SDAG-NEXT: v_mov_b32_e32 v6, v5
; SDAG-NEXT: v_mov_b32_e32 v5, v7
-; SDAG-NEXT: v_mad_u64_u32 v[4:5], s[4:5], v13, v8, v[4:5]
-; SDAG-NEXT: v_add3_u32 v3, v3, v15, v14
-; SDAG-NEXT: v_mad_u64_u32 v[1:2], s[4:5], v9, v13, v[2:3]
+; SDAG-NEXT: v_mad_u64_u32 v[4:5], s[4:5], v12, v8, v[4:5]
+; SDAG-NEXT: v_add3_u32 v3, v3, v14, v13
+; SDAG-NEXT: v_mad_u64_u32 v[1:2], s[4:5], v9, v12, v[2:3]
; SDAG-NEXT: v_add_co_u32_e64 v5, s[4:5], v6, v5
; SDAG-NEXT: v_addc_co_u32_e64 v6, s[4:5], 0, 0, s[4:5]
-; SDAG-NEXT: v_mul_lo_u32 v3, v9, v12
-; SDAG-NEXT: v_mul_lo_u32 v7, v11, v13
-; SDAG-NEXT: v_mad_u64_u32 v[5:6], s[4:5], v12, v8, v[5:6]
+; SDAG-NEXT: v_mul_lo_u32 v3, v9, v11
+; SDAG-NEXT: v_mul_lo_u32 v7, v9, v12
+; SDAG-NEXT: v_mad_u64_u32 v[5:6], s[4:5], v11, v8, v[5:6]
; SDAG-NEXT: ; implicit-def: $vgpr10
; SDAG-NEXT: ; implicit-def: $vgpr8
; SDAG-NEXT: ; implicit-def: $vgpr9
@@ -1138,7 +1133,6 @@ define i128 @fptoui_f32_to_i128(float %x) {
; SDAG-NEXT: ; %bb.2: ; %fp-to-i-if-end9
; SDAG-NEXT: v_cndmask_b32_e64 v0, 0, 1, vcc
; SDAG-NEXT: v_add_co_u32_e64 v9, s[4:5], -1, v0
-; SDAG-NEXT: v_addc_co_u32_e64 v11, s[4:5], 0, -1, s[4:5]
; SDAG-NEXT: s_mov_b64 s[4:5], 0x95
; SDAG-NEXT: v_and_b32_e32 v0, 0x7fffff, v4
; SDAG-NEXT: v_cmp_lt_u64_e64 s[4:5], s[4:5], v[5:6]
@@ -1164,24 +1158,24 @@ define i128 @fptoui_f32_to_i128(float %x) {
; SDAG-NEXT: v_cndmask_b32_e64 v2, v2, v0, s[4:5]
; SDAG-NEXT: v_lshlrev_b64 v[0:1], v4, v[6:7]
; SDAG-NEXT: v_cndmask_b32_e64 v2, 0, v2, s[6:7]
-; SDAG-NEXT: v_cndmask_b32_e64 v13, 0, v0, s[4:5]
-; SDAG-NEXT: v_cndmask_b32_e64 v12, 0, v1, s[4:5]
-; SDAG-NEXT: v_mad_u64_u32 v[0:1], s[4:5], v13, v10, 0
-; SDAG-NEXT: v_mul_lo_u32 v14, v8, v2
-; SDAG-NEXT: v_mul_lo_u32 v15, v10, v3
+; SDAG-NEXT: v_cndmask_b32_e64 v12, 0, v0, s[4:5]
+; SDAG-NEXT: v_cndmask_b32_e64 v11, 0, v1, s[4:5]
+; SDAG-NEXT: v_mad_u64_u32 v[0:1], s[4:5], v12, v10, 0
+; SDAG-NEXT: v_mul_lo_u32 v13, v8, v2
+; SDAG-NEXT: v_mul_lo_u32 v14, v10, v3
; SDAG-NEXT: v_mov_b32_e32 v6, v1
-; SDAG-NEXT: v_mad_u64_u32 v[4:5], s[4:5], v12, v10, v[6:7]
+; SDAG-NEXT: v_mad_u64_u32 v[4:5], s[4:5], v11, v10, v[6:7]
; SDAG-NEXT: v_mad_u64_u32 v[2:3], s[4:5], v10, v2, 0
; SDAG-NEXT: v_mov_b32_e32 v6, v5
; SDAG-NEXT: v_mov_b32_e32 v5, v7
-; SDAG-NEXT: v_mad_u64_u32 v[4:5], s[4:5], v13, v8, v[4:5]
-; SDAG-NEXT: v_add3_u32 v3, v3, v15, v14
-; SDAG-NEXT: v_mad_u64_u32 v[1:2], s[4:5], v9, v13, v[2:3]
+; SDAG-NEXT: v_mad_u64_u32 v[4:5], s[4:5], v12, v8, v[4:5]
+; SDAG-NEXT: v_add3_u32 v3, v3, v14, v13
+; SDAG-NEXT: v_mad_u64_u32 v[1:2], s[4:5], v9, v12, v[2:3]
; SDAG-NEXT: v_add_co_u32_e64 v5, s[4:5], v6, v5
; SDAG-NEXT: v_addc_co_u32_e64 v6, s[4:5], 0, 0, s[4:5]
-; SDAG-NEXT: v_mul_lo_u32 v3, v9, v12
-; SDAG-NEXT: v_mul_lo_u32 v7, v11, v13
-; SDAG-NEXT: v_mad_u64_u32 v[5:6], s[4:5], v12, v8, v[5:6]
+; SDAG-NEXT: v_mul_lo_u32 v3, v9, v11
+; SDAG-NEXT: v_mul_lo_u32 v7, v9, v12
+; SDAG-NEXT: v_mad_u64_u32 v[5:6], s[4:5], v11, v8, v[5:6]
; SDAG-NEXT: ; implic...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/114389
More information about the llvm-commits
mailing list